finetuned model + empathy

This commit is contained in:
Adam Wojdyla 2023-06-18 22:44:55 +02:00
parent 31538ba2c2
commit f2e09fa12f
12 changed files with 153884 additions and 2988 deletions

1
.gitignore vendored Normal file
View File

@ -0,0 +1 @@
.DS_Store

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@ -0,0 +1,3 @@
{
"<|endoftext|>": 50256
}

40
model_save/config.json Normal file
View File

@ -0,0 +1,40 @@
{
"_name_or_path": "flax-community/papuGaPT2",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.0,
"bos_token_id": 50256,
"embd_pdrop": 0.0,
"eos_token_id": 50256,
"gradient_checkpointing": false,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.0,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"torch_dtype": "float32",
"transformers_version": "4.30.2",
"use_cache": true,
"vocab_size": 50257
}

View File

@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.30.2"
}

49996
model_save/merges.txt Normal file

File diff suppressed because it is too large Load Diff

Binary file not shown.

View File

@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

100344
model_save/tokenizer.json Normal file

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,9 @@
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

1
model_save/vocab.json Normal file

File diff suppressed because one or more lines are too long